Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     freilich
    -1.00
     offenbar
    -0.92
    Herzliche
    -0.91
    прочем
    -0.89
     NDEBUG
    -0.88
     Daß
    -0.86
     ―――――
    -0.85
    Билгалдахарш
    -0.82
    というわけで
    -0.81
     unduly
    -0.79
    POSITIVE LOGITS
     alot
    0.84
     данного
    0.83
    Lets
    0.82
     cuales
    0.75
     данный
    0.74
     dimana
    0.74
     didalam
    0.74
     данной
    0.72
     disini
    0.72
     welche
    0.70
    Act Density 0.322%

    No Known Activations